Products · UnifyDrive · NAS
UnifyDrive UC450 Pro
- Processor
- Intel Core Ultra 5 225H
- Memory (RAM)
- 16 or 128 GB
- Launch price
- $1,449
- Released
- 2026
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| Intel Core Ultra 5 225H | 16.0 GB | 9.1 GB | 102 GB/s | 337 of 622 | $1,449 |
| Intel Core Ultra 5 225H · upgraded to the maker's maximum | 128 GB | 73.0 GB | 102 GB/s | 419 of 622 | — |
Specifications 128 GB configuration
| Maker | UnifyDrive |
|---|---|
| Type | NAS |
| Processor | Intel Core Ultra 5 225H NAS (128 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 128 GB |
| Usable for AI models | 73.0 GB |
| Memory bandwidth | 102 GB/s |
| FP16 compute | 8.0 TFLOPS |
| Runs models on | GPU (Vulkan) |
| Drive bays | 2x SATA + 2x SATA/U.2 + 4x M.2 NVMe |
| NAS system | UDOS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5 SO-DIMM · 2 slots · up to 128 GB per the maker · non-ECC |
| Graphics card options | External GPU: Thunderbolt 4 (2 ports); maker advertises eGPU expansion for large LLMs. |
| Notes | Intel Core Ultra 5 225H. Core Ultra 5 225H, up to 128 GB DDR5 in two slots, Docker and VMs, and maker-advertised Thunderbolt 4 eGPU expansion for LLMs |
| Product page | unifydrive.com (opens in a new tab) |
Running AI on the UnifyDrive UC450 Pro
Yes, it runs AI models on the NAS itself. Models run on its GPU (Vulkan), and this configuration leaves about 73.0 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time. More memory is the upgrade that matters most: see the configurations.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama / Open WebUI | In a container (Docker) |
AI features from UnifyDrive
| Feature | What it does | Where the AI runs |
|---|---|---|
| UDOS local AI (captions, photo and semantic search) | AI captions and natural-language photo/file search run on the NAS | On the NAS |
| UDOS local AI (photo captions, culling, semantic search) | Generates photo captions, sorts and searches media; maker describes it as local and private. | On the NAS |
Best LLMs for the UnifyDrive UC450 Pro 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 54.2 GB | 31.6 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 55.2 GB | 35.8 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 56.2 GB | 35.8 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 56.2 GB | 35.8 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q4_K_M | 30.9 GB | 42.0 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q4_K_M | 28.5 GB | 35.8 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q5_K_M | 59.7 GB | 10.8 tok/s | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q4_K_M | 28.5 GB | 35.8 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 28.1 GB | 35.8 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q4_K_M | 28.0 GB | 35.8 tok/s | Runs great |
Best Image models for the UnifyDrive UC450 Pro 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 45 s | Slow |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 19 s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 4.3 min | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP16 | 46.7 GB | 2.0 min | Slow |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 10.4 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 7.2 min | Very slow |
Best Video models for the UnifyDrive UC450 Pro 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP8 | 48.3 GB | 14.2 min | Slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | Q8 GGUF | 45.6 GB | 79.5 min | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 4.6 h | Very slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 4.6 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 2.1 h | Very slow |
Best Decision models for the UnifyDrive UC450 Pro 128 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 7.9 GB | 80 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 7.9 GB | 80 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 51 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 32 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 7.9 GB | 80 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 36 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 7.4 GB | 66 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 8.1 GB | 170 ms | Runs well |
Spec sources
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.